© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72025
    Prev
    Next
    INDEX
    Explanations

    vandalism and damage

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on words describing vandalism or willful property damage.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    轳
    -2.78
    
    -2.36
    replyreport
    -2.34
    味的
    -2.17
     fiscales
    -2.00
    複製
    -1.91
    chuckles
    -1.89
    􀂃
    -1.88
    ०
    -1.87
    ).
    -1.84
    POSITIVE LOGITS
    ↵
    2.28
    ꒥
    2.11
    蟶
    2.03
    閦
    1.97
    </h1>
    1.86
    ᠂
    1.85
     
    1.80
     tetapi
    1.76
    ことがあります
    1.74
     faſt
    1.73
    Activations Density 0.003%

    No Known Activations